Merge pull request #13 from NKeleher/rename-to-statsframe

Rename to statsframe

CONTRIBUTING.md

@@ -1,6 +1,6 @@
 # Contributing
 
-Contributions to `pydatasummary` are welcome and encouraged! The goal of this
+Contributions to `statsframe` are welcome and encouraged! The goal of this
 project is to make summarizing data and statistical models in python easier and
 more intuitive. If you have an idea for a new feature, or a bug fix, please make
 a suggestion. Every contribution is appreciated and will be considered.

Makefile

@@ -7,11 +7,11 @@ install-dev:
 style:
 	poetry run pre-commit run --hook-stage manual --all-files
 
-pytest-cov:
-	poetry run pytest --cov-report term --cov=pydatasummary tests/
+pytest-cov: install-dev
+	poetry run pytest --cov-report term --cov=statsframe tests/
 
-build: pytest-cov
+build:
 	poetry build
 
-publish: build
+publish: style build
 	poetry publish

README.md

@@ -1,42 +1,42 @@
-# pydatasummary
+# statsframe
 
 Customizable data and model summaries in Python.
 
-`pydatasummary` creates tables that provide descriptive statistics of
+`statsframe` creates tables that provide descriptive statistics of
 numeric and categorical data.
 
 The goal is to provide a simple -- yet customizable -- way to summarize
 data and models in Python.
 
-`pydatasummary` is heavily inspired by [`modelsummary`](https://modelsummary.com/)
+`statsframe` is heavily inspired by [`modelsummary`](https://modelsummary.com/)
 in R. The goal is not to replicate all that `modelsummary` does, but to provide
 a way of achieving similar results in Python.
 
-In order to achieve this, `pydatasummary` builds on the [`polars`](https://docs.pola.rs/)
+In order to achieve this, `statsframe` builds on the [`polars`](https://docs.pola.rs/)
 library to produce tables that can be easily customized and exported to other formats.
 
 ## Basic Usage
 
-As an example of `pydatasummary` usage, the `skim` function provides a
+As an example of `statsframe` usage, the `skim` function provides a
 summary of a DataFrame (either `polars.DataFrame` or `pandas.DataFrame`).
-The default summary statistics returned by `pydatasummary.skim()` are unique values,
+The default summary statistics returned by `statsframe.skim()` are unique values,
 percentage missing, mean, standard deviation, minimum, median, and maximum.
 
-Where possible, `pydatasummary` will print a table to the console and return a
+Where possible, `statsframe` will print a table to the console and return a
 polars DataFrame with the summary statistics. This allows for easy customization.
-For example, the `polars.DataFrame` with statistics from `pydatasummary` can be
+For example, the `polars.DataFrame` with statistics from `statsframe` can be
 modified using the [`Great Tables`](https://posit-dev.github.io/great-tables/reference/) package.
 
 ```python
 import polars as pl
-import pydatasummary as ds
+import statsframe as sf
 
 df = (
         pl.read_csv("https://vincentarelbundock.github.io/Rdatasets/csv/datasets/mtcars.csv")
           .drop("rownames")
     )
 
-stats = ds.skim(df)
+stats = sf.skim(df)
 
 Summary Statistics
 Rows: 32, Columns: 11
@@ -61,13 +61,13 @@ We can achieve the same result above with a pandas DataFrame.
 
 ```python
 import pandas as pd
-import pydatasummary as ds
+import statsframe as sf
 
 trees_df = pd.read_csv(
     "https://vincentarelbundock.github.io/Rdatasets/csv/datasets/trees.csv"
 ).drop(columns=["rownames"])
 
-trees_stats = ds.skim(trees_df)
+trees_stats = sf.skim(trees_df)
 
 Summary Statistics
 Rows: 31, Columns: 3
@@ -84,19 +84,19 @@ Rows: 31, Columns: 3
 ## Contributing
 
 If you encounter a bug, have usage questions, or want to share ideas to make
-the `pydatasummary` package more useful, please feel free to file an
-[issue](https://github.com/NKeleher/pydatasummary/issues).
+the `statsframe` package more useful, please feel free to file an
+[issue](https://github.com/NKeleher/statsframe/issues).
 
 ## Code of Conduct
 
-Please note that the **pydatasummary** project is released with a
+Please note that the **statsframe** project is released with a
 [contributor code of conduct](https://www.contributor-covenant.org/version/2/1/code_of_conduct/).
 
 By participating in this project you agree to abide by its terms.
 
 ## License
 
-**pydatasummary** is licensed under the MIT license.
+**statsframe** is licensed under the MIT license.
 
 ## Governance
 

docs/_quarto.yml

@@ -3,7 +3,7 @@ project:
   type: website
   output-dir: .
 # website:
-#   title: "pydatasummary"
+#   title: "statsframe"
 #   favicon: favicon.ico
 #   twitter-card: true
 #   navbar:
@@ -27,12 +27,12 @@ project:
 #   - _sidebar.yml
 
 # quartodoc:
-#   package: pydatasummary
+#   package: statsframe
 #   parser: google
 #   sidebar: _sidebar.yml
 
 #   sections:
 #     - title: "Function reference"
-#       desc: "What pydatasummary's functions do"
+#       desc: "What statsframe's functions do"
 #       contents:
 #         - skim

examples/example_datasummary_skim.py

@@ -2,14 +2,14 @@
 import pandas as pd
 import polars as pl
 
-import pydatasummary as ds
+import statsframe as sf
 
 # %%
 df = pl.read_csv(
     "https://vincentarelbundock.github.io/Rdatasets/csv/datasets/mtcars.csv"
 ).drop("rownames")
 
-stats = ds.skim(df)
+stats = sf.skim(df)
 
 # %% [markdown]
 # Import a csv file to a polars DataFrame:
@@ -26,7 +26,7 @@
 # Create a skim table
 
 # %%
-penguins_stats = ds.skim(penguins_df)
+penguins_stats = sf.skim(penguins_df)
 
 # %% [markdown]
 # Return the polars DataFrame with the summary statistics
@@ -35,15 +35,15 @@
 penguins_stats
 
 # %%
-ds.skim(
+sf.skim(
     penguins_df,
     output="markdown",
     title="Palmer's Penguins Summary Statistics",
     align="l",
 )
 
 # %%
-ds.skim(
+sf.skim(
     penguins_df,
     stats="moments",
     output="markdown",
@@ -52,7 +52,7 @@
 )
 
 # %%
-ds.skim(
+sf.skim(
     penguins_df,
     stats="full",
     output="markdown",
@@ -72,6 +72,6 @@
 trees_df.info()
 
 # %%
-trees_stats = ds.skim(trees_df)
+trees_stats = sf.skim(trees_df)
 
 # %%

pyproject.toml

@@ -1,13 +1,13 @@
 [tool.poetry]
-name = "pydatasummary"
+name = "statsframe"
 version = "0.0.2"
 description = "Customizable data and model summaries in Python."
 authors = ["Niall Keleher <niall.keleher@gmail.com>"]
 packages = [{ include = "*", from = "src" }]
 license = "MIT"
 readme = "README.md"
-homepage = "https://github.com/NKeleher/pydatasummary#readme"
-repository = "https://github.com/NKeleher/pydatasummary"
+homepage = "https://github.com/NKeleher/statsframe#readme"
+repository = "https://github.com/NKeleher/statsframe"
 keywords = ["tables", "statistics", "econometrics"]
 classifiers = [
     # https://pypi.org/classifiers/
@@ -29,6 +29,7 @@ classifiers = [
 python = "^3.9"
 polars = "^0.20.5"
 pandas = "^2.1.4"
+importlib-metadata = "^7.0.1"
 
 [tool.poetry.group.dev.dependencies]
 pytest = "^7.4.4"
@@ -40,7 +41,6 @@ bandit = "^1.7.6"
 docformatter = "^1.7.5"
 mypy = "^1.8.0"
 jupyterlab = "^4.0.11"
-importlib-metadata = "^7.0.1"
 
 [build-system]
 requires = ["poetry-core"]

src/pydatasummary/__init__.py → src/statsframe/__init__.py

@@ -1,12 +1,12 @@
-# Define pydatasummary version
+# Define statsframe version
 from importlib_metadata import version as _v
 
 # __version__ = "0.0.1"
-__version__ = _v("pydatasummary")
+__version__ = _v("statsframe")
 
 del _v
 
-# Import pydatasummary objects
+# Import statsframe objects
 # from ._tbl_data import *  # noqa: F401, F403, E402
 # from ._databackend import *  # noqa: F401, F403, E402
-from .ds import *  # noqa: F401, F403, E402
+from .datasummary import *  # noqa: F401, F403, E402

src/pydatasummary/ds.py → src/statsframe/datasummary.py

@@ -1,6 +1,6 @@
 from __future__ import annotations
 
-# Main ds imports ----
+# Main sf.imports ----
 import pandas as pd
 import polars as pl
 import polars.selectors as cs

tests/test_skim.py

@@ -1,7 +1,7 @@
 import polars as pl
 from polars.testing import assert_frame_equal
 
-from pydatasummary.ds import skim
+import statsframe as sf
 
 df = pl.DataFrame(
     {
@@ -28,7 +28,7 @@
 
 def test_skim_numeric_df(data=df):
     # Act
-    result = skim(data)
+    result = sf.skim(data)
 
     # Assert
     assert_frame_equal(result, expected_df)